LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Granite 3.0 2B Instruct by ibm-granite

 »  All LLMs  »  ibm-granite  »  Granite 3.0 2B Instruct   URL Share it on

  22609   
  Arxiv:0000.00000   Autotrain compatible Base model:finetune:ibm-granit... Base model:ibm-granite/granite...   Conversational   Granite   Granite-3.0   Instruct   Language   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ibm-granite/granite-3.0-2b-instruct 

Granite 3.0 2B Instruct Benchmarks

LMSys ELO: 1074 vs 1272 (so35)-15.6%
MMLU Pro: 20.16
GPQA: 6.6
MUSR: 1.27
BBH: 21.74
IFEval: 51.4 vs 88 (so35)-41.6%
MATH Lvl 5: 9.21
LLME Score: 0.4219
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Granite 3.0 2B Instruct (ibm-granite/granite-3.0-2b-instruct)

Granite 3.0 2B Instruct Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
Research, Commercial Applications
Applications:
AI assistants, Text classification, Summarization, Question Answering, Retrieval Augmented Generation (RAG), Code-related tasks, Function-calling, Multilingual dialog
Primary Use Cases:
General instruction response
Limitations:
Performance may not match English tasks for multilingual dialog., Requires safety testing and tuning before deployment.
Considerations:
Use with proper safety measures; introduce few-shot examples for improved outputs.
Additional Notes 
User testing across selected domains recommended to ensure safety.
Supported Languages 
English (Proficient), German (Intermediate), Spanish (Intermediate), French (Intermediate), Japanese (Intermediate), Portuguese (Intermediate), Arabic (Intermediate), Czech (Intermediate), Italian (Intermediate), Korean (Intermediate), Dutch (Intermediate), Chinese (Intermediate)
Training Details 
Data Sources:
publicly available datasets with permissive license, internal synthetic data, human-curated data
Data Volume:
Not specified
Methodology:
Supervised finetuning, reinforcement learning for model alignment, model merging
Context Length:
4096
Training Time:
Not specified
Hardware Used:
IBM's super computing cluster, Blue Vela, with NVIDIA H100 GPUs
Model Architecture:
Decoder-only dense transformer architecture, including GQA, RoPE, MLP with SwiGLU, RMSNorm, and shared input/output embeddings
Safety Evaluation 
Ethical Considerations:
May produce inaccurate, biased, or unsafe responses. Usage requires proper safety testing and tuning.
Responsible Ai Considerations 
Fairness:
Aligned to ensure safety; however, multilingual performance might not match English task performance.
Transparency:
Open source with comprehensive documentation, paper, and technical report.
Accountability:
Granite Team, IBM
Mitigation Strategies:
Few-shot examples can improve multilingual capabilities.
Input Output 
Input Format:
Structured chat format with prompts
Accepted Modalities:
text
Output Format:
Generated text response
Performance Tips:
Fine-tuning with additional examples may improve specificity and accuracy.
Release Notes 
Version:
Granite-3.0-2B-Instruct
Date:
October 21st, 2024
Notes:
Model released with refined capabilities and aligned for structured instruction following.
LLM NameGranite 3.0 2B Instruct
Repository 🤗https://huggingface.co/ibm-granite/granite-3.0-2b-instruct 
Base Model(s)  ibm-granite/granite-3.0-2b-base   ibm-granite/granite-3.0-2b-base
Model Size2b
Required VRAM5.3 GB
Updated2025-03-12
Maintaineribm-granite
Model Typegranite
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   0.3 GB: 2-of-2
Model ArchitectureGraniteForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.46.0.dev0
Tokenizer ClassGPT2Tokenizer
Padding Token<|end_of_text|>
Vocabulary Size49155
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Granite 3.0 2B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Granite 3.1 2B Instruct128K / 5.1 GB4129945
Granite 3.2 2B Instruct128K / 5.1 GB956331
Granite 3.2 2B Instruct128K / 5.1 GB712
Granite Guardian 3.1 2B128K / 5.1 GB26788
...te 3.2 2B Instruct Abliterated128K / 5.1 GB2254
...te 3.1 2B Instruct Abliterated128K / 5.1 GB594
Note: green Score (e.g. "73.2") means that the model is better than ibm-granite/granite-3.0-2b-instruct.

Rank the Granite 3.0 2B Instruct Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 44949 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer